Instructions to use XingChen-AGI/Xing4.0-29B-A4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XingChen-AGI/Xing4.0-29B-A4B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="XingChen-AGI/Xing4.0-29B-A4B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("XingChen-AGI/Xing4.0-29B-A4B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use XingChen-AGI/Xing4.0-29B-A4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XingChen-AGI/Xing4.0-29B-A4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XingChen-AGI/Xing4.0-29B-A4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XingChen-AGI/Xing4.0-29B-A4B

SGLang

How to use XingChen-AGI/Xing4.0-29B-A4B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "XingChen-AGI/Xing4.0-29B-A4B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XingChen-AGI/Xing4.0-29B-A4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "XingChen-AGI/Xing4.0-29B-A4B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XingChen-AGI/Xing4.0-29B-A4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XingChen-AGI/Xing4.0-29B-A4B with Docker Model Runner:
```
docker model run hf.co/XingChen-AGI/Xing4.0-29B-A4B
```

Minimum number of A100/H100 GPUs to serve Xing4.0-29B-A4B at full 256K context?

by rtudriny - opened 8 days ago

Discussion

rtudriny

8 days ago

Hi team, could you give a straightforward deployment answer:

How many GPUs do we need to serve this model with the full 256K context ? e.g. is 4×A100/H100 80G (TP=4) enough, or do we need 8×80G (TP=8)?
Same question for the 512K extended context, if anyone has tested it.

The model card says 256K support, but doesn't state the hardware requirement. A simple "N×80G GPUs for 256K" line would help a lot for capacity planning. Thanks!

hanzceo

8 days ago

Standard 256k requires about 11.25GiB of VRAM (ref)
My estimated requirement for 512k context window is about 22.50GiB of VRAM

1x80G GPU might be overkill for a single user

Prophet000

XingChen-AGI org 7 days ago

Good news — a single H100 80G can reach or come close to the full 256K context at one concurrent request. For 512K, you'll need roughly double the KV cache headroom, so a 2×H100 80G setup gives you more comfortable headroom and better cost-efficiency overall.

This matches the estimate above — thanks for the KV cache calculation, that lines up with our internal numbers.

Quick note: actual VRAM usage depends on quantization choice and framework overhead. If you share your expected concurrency and quant plan, I can help you size it more precisely.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment